A 2.8 MB byte-level transformer for GUI form filling. For each form element it returns one probability per typed option (fill an entity, check, click or skip), using jevlike's option-attention head.
A 144M-parameter System One model on the multilingual mmBERT-small encoder. Takes a state, a question and 2 to 20 options and returns one decision with probabilities for choice, score and yes/no questions, on a CPU.
Decides
choice
choice, score, noul, classify, route
Architecture
cua-s1
julia
Fine-tuned from
—
jhu-clsp/mmbert-small
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
100.0%
73.2%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
Evaluation suite
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between cua-s1-forms and julia-1?
cua-s1-forms is from Cua and julia-1 from Supersonic Labs. Both have open weights you can download and run. Both answer choice questions. Only julia-1 answers score, noul, classify and route. cua-s1-forms is the smaller model, at 706K parameters to 144M. cua-s1-forms is licensed mit; julia-1, apache-2.0.
Which is more accurate, cua-s1-forms or julia-1?
They report on different suites — cua-s1-forms 100.0% on 196-decision evaluation on real forms, julia-1 73.2% on typed-decisions test set (400 cases, 2,000 questions) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cua-s1-forms or julia-1?
cua-s1-forms: Free (open weights). julia-1: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run cua-s1-forms or julia-1 locally?
Yes, both: systemone pull cua/cua-s1-forms and systemone pull supersonic-labs/julia-1 download the weights.
196-decision evaluation on real forms
typed-decisions test set (400 cases, 2,000 questions)
